Eye-Movement Elevator Floor Selection Without Button Contact
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Elevator buttons are troublesome for individuals carrying heavy objects or in crowded conditions, and they pose a risk for virus transmission during influenza seasons.
Innovation Solution
A method and apparatus for non-contact elevator floor selection using eye-movement input, involving face detection, binocular position localization, and a generative adversarial network to calculate line-of-sight direction and trigger buttons based on dwell time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If physical buttons are used for elevator floor selection, then the control mechanism is simple and reliable, but it requires physical contact which poses virus transmission risk and is troublesome for users carrying heavy objects or in crowded conditions
Solution Approach 1:
The patent replaces the mechanical button-pressing system with an optical recognition system using cameras and deep learning algorithms. The system captures images of the user's line of sight, processes them through neural networks to determine which floor the user is looking at, and automatically triggers the corresponding floor selection without any physical contact with buttons.
Solution Approach 2:
The patent introduces an intermediary optical measurement system between the user and the button panel. Instead of direct contact with buttons, the system uses cameras to capture visual information about the user's gaze direction, processes this information through image processing and deep learning, and uses the results to control elevator floor selection indirectly.
2Ease of operation
If physical buttons are used for elevator floor selection, then the device structure is simple, but it requires physical contact which is troublesome for users carrying heavy objects
Solution Approach 1:
The patent replaces the simple mechanical button system with a complex optical recognition system involving multiple cameras, image processing units, and deep learning models. This substitution eliminates the need for physical contact while automatically determining floor selection based on the user's line of sight.
Solution Approach 2:
The system enables the elevator to automatically determine the user's intended floor selection by analyzing the user's gaze direction. The elevator system serves itself by interpreting visual cues from the user, eliminating the need for manual button pressing and providing a hands-free operation experience.
3Reliability
If physical buttons are used for elevator floor selection, then the control system is simple, but it poses virus transmission risk during influenza seasons
Solution Approach 1:
The patent replaces the mechanical button interface with a contactless optical recognition system. Cameras capture images of the user's eyes and line of sight, which are then processed through image processing and deep learning algorithms to determine the selected floor, completely eliminating the need for physical contact with potentially contaminated surfaces.
Solution Approach 2:
The patent introduces an optical measurement intermediary that stands between the user and the elevator control system. Instead of direct contact with buttons, the system uses visual measurement of the user's gaze direction as an intermediate step to determine floor selection, thereby preventing virus transmission while maintaining reliable control.
Data Source
AI summary
The present disclosure discloses systems, methods and an apparatus for non-contact and eye-movement input of an elevator floor, which comprises: selecting a target camera according to a distance sensor installed on a button panel inside the elevator; triggering a corresponding target camera by using the distance sensor for face detection; standardizing a detected human face and locating a binocular position; inputting data of a standardized human face image and a binocular image into a preset posture discriminator to obtain a predicted head posture and an eyeball posture; according to the head posture and the eyeball posture, calculating a line-of-sight direction and a coordinate of an attention point, detecting whether a dwell time of the line-of-sight is greater than a preset time threshold, and, if so, triggering a button at the coordinate of the attention point.